Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 11066
    Prev
    Next
    INDEX
    Explanations

    phrases describing something as "cool."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     smtplib
    -0.76
    harusnya
    -0.66
    WebRequest
    -0.64
     vivement
    -0.61
     улыб
    -0.60
    garmin
    -0.60
    amqp
    -0.60
     assise
    -0.60
     Elasticsearch
    -0.58
    XPATH
    -0.58
    POSITIVE LOGITS
     cool
    3.40
     Cool
    3.35
    cool
    3.26
    Cool
    3.22
     COOL
    3.11
    COOL
    2.86
     cools
    2.66
     coolness
    2.51
     coolest
    2.51
     cooler
    2.46
    Activations Density 0.051%

    No Known Activations